Online stores

AI agent for WooCommerce sales on Messenger

An AI agent answers private Messenger messages, clarifies the product the customer wants and checks the WooCommerce item and variant.

Explore the AI agent on other channels

The customer context

Do you have the Desk lamp in white?

A customer reacts to a Facebook offer but gives only part of the name. Telp clarifies the product and variant before checking, avoiding an answer about the wrong item.

What remains after the conversation

The AI agent created order WC-302 with the selected items, contact details and collection choice. Payment is due at the shop.

Your store Messenger
  1. Customer

    Do you have the Desk lamp in white?

  2. Telp

    Yes, white Desk costs 2,900 RSD. To order for shop collection, please share the quantity, name, email and phone. Please include your billing address.

  3. Customer

    I'd like one white Desk lamp. Collection and payment at the shop. Ana Example, [email protected], +381 60 0000000. Billing address: Example Street 10, 11000 Belgrade, Serbia.

  4. Telp

    Ana, order WC-302 is created: one white Desk lamp. The total is 2,900 RSD, payable on collection.

From a question to the next step

  1. 01

    The customer selects a product and receives its price.

  2. 02

    The customer provides contact details and chooses collection and payment.

  3. 03

    The agent creates the order and reports its number after the store confirms it.

Connect a Facebook question to the right WooCommerce item

The AI agent first clarifies which lamp, model or colour the customer wants. It then checks available store data and explains the next step. Access to the range is described under WooCommerce integration.

A private conversation can prepare a purchase or a question for an employee, but a post or comment is not a Messenger chat. Customers contacting the brand on Instagram have a separate Instagram sales flow.

The customer refers to several similar lamps

The agent asks for the model and desired colour. An answer about one model should not be applied to every product in the collection.

The customer expects a price from an earlier post

The price is checked against the available source. The agent should not reinstate an old promotion simply because the customer mentions it.

An AI agent across channels

WordPress / WooCommerce customers ask in more than one place

An AI agent can use your connected WooCommerce catalog for questions on Messenger, Instagram, WhatsApp, Viber, Telegram and website chat. Browser calls and phone enquiries use their respective voice flows. Explore what the agent does on each channel.

Each channel needs its own connection and verification. Catalog access does not automatically enable ordering or payment on every channel; available actions and confirmations depend on the configured flow.

FAQ

Frequently asked questions

Does a public comment start an order?

Not in this scenario. The customer uses private Messenger messages, and purchasing follows a separately configured flow.

Does the agent check the actual WooCommerce range?

It uses the connected catalog and data available for the particular check. Source freshness and correct product identification need verification.

Do we need a new catalog for Facebook?

This scenario uses the WooCommerce source. Connecting the Facebook page and enabling conversation access are still separate setup steps.

Can a customer order through Messenger?

Only through a supported, configured flow with required details and a permitted action. A private message alone does not create an order.

What if the customer wants to exchange a purchased item?

The agent can collect the order identifier and reason. Approval and execution of an exchange remain separate from catalog lookup.

Can the same store also answer on Instagram?

Yes, with a separately connected Instagram channel. Appropriate WooCommerce access is used, with the channel's sales flow checked separately.

Want to validate this workflow with your own examples?

Tell us the channel, current process and first result you want to improve. We will suggest a focused rollout path and the cases your team should test.